检索结果-内蒙古大学图书馆

Performance Evaluation of a Multi-input Interleaved boost Converter with a Tuned Proportional-integral Controller

Chinese Journal of Electrical engineering 2024年第4期10卷 119-128页

作者： Sucharita Pal Dola Sinha Mou Das Mahapatra Saibal Majumder Sovan bhattacharya Chan byopadhyay Department of Electrical Engineering Asansol Engineering CollegeAsansol 713305India Department of Electrical Engineering Dr.B.C.Roy Engineering CollegeDurgapur 713206India Department of Computer Science and Engineering(Data Science) Dr.B.C.Roy Engineering CollegeDurgapur 713206India Department of Computer Science and Engineering University of BremenBremen 28359Germany

The need for renewable energy access has led to the use of variable input converter approaches because renewable energy sources often generate electricity in an unpredictable manner. A high-performance multi-input boost converter is developed to provide the necessary output voltage and power while accommodating variations in input sources. This converter is specifically designed for the efficient usage of renewable energy. The proposed architecture integrates three separate unidirectional input power sources: photovoltaics, fuel cells, and storage system batteries. The architecture has five switches, and the implementation of each switch in the converter is achieved by applying the calculated duty ratios in various operating states. The closed-loop response of the converter with a proportional-integral (PI) controller-based switching system is examined by analyzing the Matlab-Simulink model utilizing a proportional-integral derivative (PID) tuner. The controller can deliver the desired output voltage of 400 V and an average power of 2 kW while exhibiting low switching transient effects. Therefore, the proposed multi-input interleaved boost converter demonstrates robust results for real-time applications by effectively harnessing renewable power sources.

关键词： Multi-input converter interleaved boost converter pulse-width modulation proportional-integral controller

来源：评论

学校读者我要写书评

暂无评论

Handwritten optical character recognition using TransRNN trained with self improved flower pollination algorithm (SI-FPA)

引用

Multimedia Tools and Applications 2025年第18期84卷 19947-19969页

作者： Devi, S. Nandhini Fatima, N. Sabiyath Department of Computer Science and Engineering B.S. Abdur Rahman Crescent Institute of Science & Technology Chennai India

The difficulty of successfully scanning handwritten text arises from variances in style, size, and orientation, which affect handwriting optical character recognition (OCR). This study provides a novel strategy that incorporates innovative techniques for effectively addressing these difficulties. Initially, preprocessing steps involve Gaussian blur to reduce noise and CLAHE to enhance contrast, improving the visibility of text regions. Canny Edge Detection is then utilized for segmentation, followed by text localization using the Efficient and Accurate Scene Text (EAST) algorithm. Next, features are extracted via Inception V3 to capture both low-level and high-level information. From the collected characteristics, Long Short-Term Memory (LSTM) networks are used to extract chronological data. Then, with the help of the Self-Improved Flower Pollination Algorithm (SI-FPA), features are selected using Optimized Principal Component Analysis (PCA). Finally, a combination of Transformer and Recurrent neural networks (RNNs) is used to perform text recognition, maximizing the benefits of each network’s advantages in processing sequential and contextual data. Experiments on MNST dataset with validation using different optimization algorithms show the effectiveness and resilience of the suggested method in different optimization scenarios. The combination of these methods results in a sophisticated OCR system that can recognize handwritten characters with accuracy, even under difficult conditions. © The Author(s), under exclusive licence to Springer science+business Media, LLC, part of Springer Nature 2024.

关键词： Principal component analysis

来源：评论

学校读者我要写书评

暂无评论

Photovoltaic power one-day and multistep-hourly AI predictions using node-by-node evolved binomial tree structures to form L-transformed PDE modules

引用

Soft Computing 2025年第5期29卷 2483-2495页

作者： Zjavka, Ladislav Department of Computer Science Faculty of Electrical Engineering and Computer Science VŠB-Technical University of Ostrava 17. Listopadu 15/2172 Ostrava Czech Republic

Photovoltaic (PV) power is generated by two common types of solar components that are primarily affected by fluctuations and development in cloud structures as a result of uncertain and chaotic processes. Local PV forecasting is unavoidable in supply and load planning necessary in integration of smart systems into electrical grids. Intra- or day-ahead modelling of weather patterns based on Artificial Intelligence (AI) allows one to refine available 24 h. cloudiness forecast or predict PV production at a particular plant location during the day. AI usually gets an adequate prediction quality in shorter-level horizons, using the historical meteo- and PV record series as compared to Numerical Weather Prediction (NWP) systems. NWP models are produced every 6 h to simulate grid motion of local cloudiness, which is additionally delayed and usually scaled in a rough less operational applicability. Differential Neural Network (DNN) is based on a newly developed neurocomputing strategy that allows the representation of complex weather patterns analogous to NWP. DNN parses the n-variable linear Partial Differential Equation (PDE), which describes the ground-level patterns, into sub-PDE modules of a determined order at each node. Their derivatives are substituted by the Laplace transforms and solved using adapted inverse operations of Operation Calculus (OC). DNN fuses OC mathematics with neural computing in evolution 2-input node structures to form sum modules of selected PDEs added step-by-step to the expanded composite model. The AI multi- 1…9-h and one-stage 24-h models were evolved using spatio-temporal data in the preidentified daily learning sequences according to the applied input–output data delay to predict the Clear Sky Index (CSI). The prediction results of both statistical schemes were evaluated to assess the performance of the AI models. Intraday models obtain slightly better prediction accuracy in average errors compared to those applied in the second-day-ahead

关键词： Laplace transforms

来源：评论

学校读者我要写书评

暂无评论

Assessing the predictive power of boosting techniques for diabetes

引用

Multimedia Tools and Applications 2025年 1-25页

作者： V, Umadevi G A, Yashaswini Department of Computer Science and Engineering B.M.S. College of Engineering Bull Temple Road Karnataka Bangalore560019 India

Diabetes affects more than half a million individuals globally. Diabetes can cause heart attacks, renal damage, and even blindness. Machine learning algorithms, with their intelligence capacity can precisely anticipate diabetes and prevent its complications which will allow premature detection of diabetes. boosting techniques offer a powerful approach to machine learning by combining weak models to form a strong ensemble. They excel in addressing challenging classification tasks and can significantly improve predictive performance compared to individual models. This study investigates the predictive efficacy of two widely recognized boosting techniques, namely Adaboost (Ab) and Gradientboost (Gb), across four distinct diabetes datasets. The selected datasets include Pima diabetes dataset (PDD), Early stage diabetes dataset (EDD), Mendeley Diabetes dataset (MDD), and bFRSS Diabetes dataset (bDD), to facilitate comprehensive analysis and investigation for diabetes classification. Among the two boosting techniques, the fine tuned Gb showed highest performance with respect to Accuracy, Precision, Recall, F1-score, AUC score, MSE (Mean Squared Error), G-Mean (Geometric Mean), Kappa, MCC (Mathews Correlation Coefficient) for diabetes classification on all four diabetes datasets. The accuracy of prediction on four datasets obtained by Gb was 87.66%, 98.07%, 99.00% and 85% respectively. © The Author(s), under exclusive licence to Springer science+business Media, LLC, part of Springer Nature 2025.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Assessing classification approaches for categorizing Ayurvedic herbs

引用

Multimedia Tools and Applications 2025年第9期84卷 6711-6735页

作者： Umadevi, V. Kamath, Vaishnavi Department of Computer Science and Engineering B.M.S. College of Engineering Bull Temple Road Karnataka Bangalore560019 India

Ayurvedic herbs hold immense importance in traditional Ayurvedic medicine. These herbs are considered vital elements in maintaining physical, mental, and spiritual balance in the human body. According to ayurveda, diseases arise due to imbalances in doshas namely Vata, Pitta, and Kapha. Ayurvedic practitioners diagnose diseases by analyzing the dosha imbalances in an individual’s body and mind. Ayurvedic herbs play a crucial role in balancing the doshas and promoting overall health and well-being. Each herb possesses specific properties that can either pacify or aggravate the three *** research employs machine learning models to classify Ayurvedic herbs according to their dosha balancing properties. Using a 90-10 split, the data was randomly split into a training set and a test set. Data preprocessing using random oversampling and artificial sample generation using CTGAN is also performed on the dataset. A total of six experiments are performed on the dataset. Various classification models like SVM, KNN, RF, DT and XGboost were used for classification. Using four target classes without oversampling, the XGboost classifier yielded the best classification models with an impressive accuracy of 96%, Precision of 97%, Recall of 96%, F1-score of 96% and Root mean square error of 0.16. The experimental results provide compelling evidence that the proposed model, which uses ensemble learning methods, significantly outperforms conventional methods. © The Author(s), under exclusive licence to Springer science+business Media, LLC, part of Springer Nature 2024.

关键词： Learning systems

来源：评论

学校读者我要写书评

暂无评论

Security enhancements in M-health using distributed ledger technology based digital locker system

引用

International Journal of Information Technology (Singapore) 2024年第7期16卷 4253-4271页

作者： Ray, Soumya Mishra, Kamta Nath Dutta, Sandip Department of Computer Science and Engineering B.I.T. Mesra

Electronic Medical Records (***) comprise sensitive and private information of the patients in m-healthcare, and the passing of data across different medical institutions poses severe challenges. Leakage of information could destroy the privacy of the data, and the availability of the data at runtime may be disrupted by the DDoS (Distributed Denial of Service) attack. Distributed Ledger Technology (DLT) helps overcome the challenges of the trusted decentralized database. It is possible to validate all the stakeholders by a single-step authentication process using distributed ledger technology. In this research paper, the authors have proposed a distributed ledger technology architecture (DLTA) using an m-health digital locker (DL) system and presented the interaction of the different m-healthcare entities with the anticipated model. The authors have designed the mathematical model to enhance the security re-assurance of the DLTA-based m-health DL system. The security analysis of the proposed model is highlighted and compared the same with the non-distributed system architecture. The key factors considered for evaluating the proposed model are network congestion, throughput, average turnaround time, average response time, average waiting time, and network consumption. © bharati Vidyapeeth's Institute of computer Applications and Management 2024.

关键词： Distributed denial of service attacks Distributed ledger technology-based digital locker M-healthcare systems Network security Sensitive data

来源：评论

学校读者我要写书评

暂无评论

Hybrid approaches for handling imbalanced structured and unstructured data

引用

Multimedia Tools and Applications 2024年 1-23页

作者： Akshay, M. Manu, Rishabh Raj, Rishika Suhas, K.T. Shobha, K. Department of Computer Science and Engineering Siddaganga Institute of Technology B.H Road Karnataka Tumkur572102 India

With their limitless potential for highly accurate decision-making behaviors, machine learning algorithms have emerged to influence the world of information systems. Algorithms designed for structured and unstructured data sets do not produce good results if the data set has an uneven distribution of classes (imbalanced), this is because these algorithms are designed and developed to generalize from training data samples and to produce the most accessible hypothesis that fits the data. Uneven distribution of classes in the training stage gives a low precision on the minority class(es) but a high accuracy on the majority class(es) resulting in high-cost losses or even catastrophes. To overcome this inevitability, this work aims to propose hybrid balancing techniques. Proposed hybrid approaches have been empirically evaluated on both structured and unstructured imbalanced data sets. Empirical results have shown that the proposed hybrid approaches have outperformed state-of-the-art techniques by achieving improved mean recall rates of 40% and 20% on Pima diabetes and Cerebral stroke structured data sets respectively. The proposed method has also outperformed in balancing unstructured data by generating minority class data with the similarity (measured using Structural Similarity Index Measure (SSIM)) ranging between 25%-60% on MNSIT and Fashion-MNIST data sets. The resultant balanced dataset is further evaluated using conventional classification algorithms, where the outcomes on balanced dataset have shown a performance improvement of 10% compared to imbalanced data. © The Author(s), under exclusive licence to Springer science+business Media, LLC, part of Springer Nature 2024.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

A proactive load balanced handoff scheme for vehicular ad-hoc networks

引用

International Journal of Vehicle Information and Communication Systems 2023年第4期8卷 345-362页

作者： Madli, Rajeshwari Varaprasad, G. Department of Computer Science and Engineering B.M.S. College of Engineering Bengaluru Karnataka Bangalore India

The embracement of the wireless technology by the automobile industry has led to novel research interests in the field of Vehicular Ad-hoc Networks (VANETs). In addition to ad-hoc mode, a VANET supports infrastructure mode of communication, which provides access to internet services such as Hyper Text Transfer Protocol (HTTP), Voice over Internet Protocol (VoIP) and File Transfer Protocol (FTP), through access points known as Road Side Units (RSU). Vehicles can benefit from these services when associated with an RSU. However, because of uneven distribution and high mobility of vehicles, some RSUs are overloaded, resulting in network congestion and affecting the packet delivery ratio and throughput. This paper proposes a proactive load-balanced handoff scheme, in which vehicles evade overloaded RSUs and choose an RSU based on signal strength, network load and service reliability. Simulation results indicate that vehicles using the load-balanced handoff method, experience a higher packet delivery ratio and throughput. Copyright © 2023 Inderscience Enterprises Ltd.

关键词： Vehicular ad hoc networks

来源：评论

学校读者我要写书评

暂无评论

HarvestHub: Mobile Agricultural Markets 7

HarvestHub: Mobile Agricultural Markets

引用

7th International Conference on Circuit Power and Computing Technologies, ICCPCT 2024

作者： Deepika, Gundaboina begum, Heena Reddy, Gangireddy Niranjan Joshini, Gogulamanda Sathyanarayanan, D. Pallavi, L. B V Raju Institute of Technology Department of Computer Science and Engineering Telangana India B V Raju Institute of Technology Department of Computer Science and Engineering Telangana India

ISBN: (纸本)9798350372816

This project aims to develop a web application addressing challenges in agricultural marketing, leveraging technology to connect farmers directly with buyers. Recognizing technology's pervasive role and potential impact, the project seeks to create a user-friendly platform for agricultural *** project will employ a comprehensive approach, considering technical development and socio-economic contexts. It begins with analysis of existing systems, informed by literature review and consultations. Iterative cycles of design, implementation, and testing guided by user feedback will be conducted. Key features include support for a local language, secure payments, customizable categorization, and intuitive interface *** project aims to produce a web application tailored for agricultural marketing. It will provide farmers a platform to showcase products and offer buyers convenient access. by streamlining processes, the application intends to enhance market access, improve transparency, and contribute to sector growth and *** by a commitment to leveraging technology for social good, this project seeks to empower farmers and promote economic development. Through stakeholder collaboration and ongoing evaluation, it aims for sustainability and scalability. © 2024 IEEE.

关键词： Agricultural economics

来源：评论

学校读者我要写书评

暂无评论

Performance Analysis of Machine Learning based On Optimized Feature Selection for Type II Diabetes Mellitus

引用

Multimedia Tools and Applications 2025年第8期84卷 4945-4964页

作者： bhat, Salliah Shafi Ansari, Gufran Ahmad Ansari, Mohd Dilshad B. S. Abdur Rahman Crescent Institute of Science and Technology Chennai48 India Department of Computer Science and Software Engineering University of Hail Hail55424 Saudi Arabia Department of Computer Science & Engineering SRM University Delhi-NCR Harayana Sonepat131029 India

Type 2 Diabetes Mellitus (T2DM) is a common chronic illness caused by variations in the secretion of insulin. T2DM will be treated early with the help of an early diagnosis reducing the risk of early death and controlling is course of illness. In this Paper Machine Learning Algorithms (MLA) for T2DM diagnosis are proposed. The major objective of this research is to assess use of MLA and its methods to forecast different illnesses at an initial stage. In this research, we examine most recent proposed strategies with some limitations and potential improvements for future work. The data is collected from Kaggle (University of California) *. Researchers highlight how important is to identify important features that enhance outcomes suggested by recent methods. Six MLA were used in this paper such as Logistic Regression (LR), Support Vector Machine (SVM), Naive bayes (Nb), Decision Tree (DT), Random Forest (RF) and K-Nearest Neighbour (KNN) were applied in Jupiter Notebook. Feature sets are selected using three feature selection methodologies such as information gain-based selection, correlation-based selection and sequential feature selection. On these feature subsets a variety of MLA are applied and optimal feature subset is chosen based on their performance. Finally a DT is suggested as the top model among the top six performances. The suggested method provides an improved performance label with an average accuracy of 96.10%. © The Author(s), under exclusive licence to Springer science+business Media, LLC, part of Springer Nature 2024.

关键词： Feature Selection

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：